AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Learning Global Nash Equilibrium in Team Competitive Games with Generalized Fictitious Cross-Play

Zelai Xu, Chao Yu, Yancheng Liang, Yi Wu, Yu Wang

JMLR 2025 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GFXP counter population instead of SPMAgent Battle 3-vs-3 agents · MAgent Battle 3-vs-3exploitability: 28.66 -> 10.62Improved
add GFXP counter population instead of SPMAgent Battle 10-vs-5 agents · MAgent Battle 10-vs-5exploitability: 42.21 -> 18.92Improved
use GFXP instead of PSRONashMAgent Battle agents · MAgent Battle 10-vs-5exploitability: 44.88 -> 18.92Improved
use GFXP instead of ODOMAgent Battle agents · MAgent Battle 3-vs-3exploitability: 21.76 -> 10.62Improved
use GFXP instead of SPGRF Academy agents · GRF Academy PS 2-vs-1exploitability: 0.75 -> 0.35Improved
use GFXP instead of ODO (strongest baseline)GRF Academy agents · GRF Academy HCA 4-vs-2exploitability: 0.44 -> 0.33Improved
use GFXP instead of ODOGRF Academy agents · GRF Academy RPS 2-vs-1exploitability: 0.71 -> 0.60Improved
add reset (retrain from scratch each iteration) to GFXP (ablation)GFXP · SAD gamesteps to converge: 523 -> 943Hurt
remove warm start (reset) in PSRO and ODO (ablation)PSRO and ODO · SAD gameconvergence to global NE: converge to global NE -> degenerate to SP-like performanceHurt
larger self-play ratio eta (0.8, 1) (ablation)GFXP · SAD gameconvergence to global NE: eta=0.8, 1 converge to local NE; eta=0, 0.2, 0.4, 0.6 converge to global NEHurt
use decaying eta (linear 1 to 0 in 5 iterations) instead of fixed eta (ablation)GFXP · SAD gamesteps to convergeImproved
increase game scale (actions A = 5, 10, 15, 20) (ablation)GFXP · SAD gamesteps to converge: A = 5, 10, 15, 20; converges in all runsMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy